© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 14920
    Prev
    Next
    INDEX
    Explanations

    connections related to technology and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     automatic
    -0.06
    even
    -0.06
     myself
    -0.06
     дÑĥ
    -0.06
    ADR
    -0.06
    ake
    -0.06
     early
    -0.06
    ëĿ¼ëıĦ
    -0.05
    ساÙĦ
    -0.05
     mark
    -0.05
    POSITIVE LOGITS
     ultimately
    0.08
     various
    0.08
    indow
    0.07
    ä¸ĢåĪĩ
    0.07
    ippers
    0.07
     amet
    0.07
    ToFit
    0.07
    .scalablytyped
    0.07
    776
    0.07
     cÃł
    0.07
    Activations Density 0.039%

    No Known Activations